Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 8690
    Prev
    Next
    INDEX
    Explanations

    web addresses starting with "//"

    oai_token-act-pair · gpt-3.5-turbo

    URL-related patterns or characters in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tsunami
    -0.92
     tide
    -0.85
    phrine
    -0.85
     livest
    -0.84
    ĺħ
    -0.83
     predatory
    -0.83
    ylum
    -0.80
     satell
    -0.78
     probation
    -0.77
     strugg
    -0.73
    POSITIVE LOGITS
    ////////////////
    1.18
    ////////
    1.16
    ////////////////////////////////
    1.12
    ++++++++++++++++
    1.08
    wcsstore
    1.04
    ////
    0.97
    ================================================================
    0.89
    ãĤ§
    0.83
    Untitled
    0.81
    nee
    0.80
    Activations Density 0.008%

    No Known Activations